Open AccessEnsemble classification based COVID-19 diagnosis from chest X-rays and CT images
Author(s) -
Monelli Ayyavaraiah,
Bondu Venkateswarlu
Publication year - 2022
Publication title -
international journal of health sciences (ijhs) (en línea)
Language(s) - English
Resource type - Journals
eISSN - 2550-6978
pISSN - 2550-696X
DOI - 10.53730/ijhs.v6ns3.5905
Subject(s) - overfitting , artificial intelligence , feature (linguistics) , covid-19 , benchmark (surveying) , computer science , machine learning , ensemble learning , radiography , curse of dimensionality , pattern recognition (psychology) , disease , medicine , radiology , artificial neural network , pathology , cartography , geography , infectious disease (medical specialty) , linguistics , philosophy
COVID-19 continues to have catastrophic impacts on human beings lives all over the world. To fight with this disease, it has been required to screen the impacted patients rapidly with less false alarming. Moreover, the significant feasible steps to attain this objective are computer-aided methods of machine learning strategies trained by the features of the CT and chest X-ray images. However, these features’ high dimensionality becomes a critical issue that often reflects as high in false alarming in disease scope prediction. Concerning to the stated argument, this contribution endeavored to portray an ensemble learning-based machine learning approach to reduce the feature overfitting due to of high dimensionality in training-corpus for COVID-19 disease prediction with minimal false alarming. The proposed method’s cross-validation using benchmark dataset evincing the minimal false alarming in COVID-19 disease prediction using high dimensional features of the radiographic test reports (x-ray and CT-images).